home / mcp / amazon redshift mcp server

Amazon Redshift MCP Server

Provides read-only access to live Amazon Redshift data via MCP, enabling natural-language queries and data exploration.

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "cdatasoftware-amazon-redshift-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/amazon-redshift.prp"
      ]
    }
  }
}

You can query live Amazon Redshift data through a lightweight MCP server that exposes the data as MCP tools. This enables language models to read from Redshift in real time without writing SQL, while keeping access controlled and straightforward to use.

How to use

You connect to your MCP server locally and then ask the AI to retrieve or summarize data from Redshift. The server presents read-only access via built‑in tools such as listing available tables, listing columns for a table, and running read queries. You don’t need to write SQL yourself; just ask natural language questions and let the AI compose the queries.

How to install

Prerequisites you need on your machine: the Java runtime and Maven for building the server.

Step 1: Clone the project and navigate into it.

git clone https://github.com/cdatasoftware/amazon-redshift-mcp-server-by-cdata.git
cd amazon-redshift-mcp-server-by-cdata

Step 2: Build the server to produce the MCP jar.

mvn clean install

Step 3: Obtain and license the CData JDBC Driver for Amazon Redshift. Download from the vendor and install it on your system following the driver’s instructions.

Step 4: Create a connection string with the JDBC driver and save it to a properties file (for example amazon-redshift.prp). This file should include your driver path, driver class, and the JDBC URL, as well as which tables to expose (blank to expose all). Example properties content is shown below.

Prefix=redshift
ServerName=CDataRedshift
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.redshift.jar
DriverClass=cdata.jdbc.redshift.RedshiftDriver
JdbcUrl=jdbc:redshift:InitiateOAuth=GETANDREFRESH;
Tables=

Run the MCP server from your build

Step 5: Start the MCP server using the generated jar and your .prp file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/amazon-redshift.prp

Available tools

redshift_get_tables

Retrieves a list of tables available in the Redshift data source. The output is provided in CSV format with column headers.

redshift_get_columns

Retrieves a list of columns for a specified table. The output is provided in CSV format with column headers.

redshift_run_query

Executes a SQL SELECT query against the Redshift data source and returns the result set.